CN208622096U - A kind of translation system - Google Patents
A kind of translation system Download PDFInfo
- Publication number
- CN208622096U CN208622096U CN201820906466.1U CN201820906466U CN208622096U CN 208622096 U CN208622096 U CN 208622096U CN 201820906466 U CN201820906466 U CN 201820906466U CN 208622096 U CN208622096 U CN 208622096U
- Authority
- CN
- China
- Prior art keywords
- transcription
- client
- text
- speech
- server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
This application provides a kind of translation systems, it include: server, and with assistant's client of server communication connection and client of attending a meeting, wherein: server, for being translated to the speechmaker's voice received, the cypher text of speechmaker's voice is sent to assistant's client, and receives first translated speech of the interpreter based on speechmaker's voice output；Assistant's client, is used by interpreter, for showing cypher text, is translated and is referred to for the interpreter；It attends a meeting client, for receiving first translated speech of server transmission, and plays the first translated speech.The application interpreter further can translate speechmaker's voice, compared with the existing technology, improve the accuracy rate of translation and reduce the cost of simultaneous interpretation in conjunction with server to the translation result of speechmaker's voice.
Description
Technical field
This application involves interpreting equipment technical field, in particular to a kind of translation system.
Background technique
Currently, being mainly accomplished manually by interpreter in the simultaneous interpretation of simultaneous interpretation industry, start to say 2 to 3 in spokesman
When word, interpreter synchronizes translation and broadcasts and listens to personnel participating in the meeting.
Since meeting has relevant main body and field, many technical terms, industry name are had, and be limited to spokesman
Accent, interpreter the factors such as vocabulary, the instantaneity of translation so that the accuracy rate generally translated is 80% or so；Meanwhile by
In interpreter's great work intensity, a simultaneous interpretation meeting is generally required 2 to 3 interpreters and was limited with 20 minutes translates in turn,
Cause the investment of a large amount of manpower and financial resources.
Utility model content
In order to solve the above technical problems, the embodiment of the present application provides a kind of translation system, interpreter can combine server
To the translation result of speechmaker's voice, further speechmaker's voice is translated, compared with the existing technology, improves translation
Accuracy rate and the cost for reducing simultaneous interpretation, technical solution are as follows:
A kind of translation system, comprising: server, and with assistant's client of the server communication connection and the client that attends a meeting
End, in which:
The server, for being translated to the speechmaker's voice received, by the translation text of speechmaker's voice
Originally it is sent to assistant's client, and receives the first translated speech of the interpreter based on speechmaker's voice output；
Assistant's client, is used by interpreter, for showing the cypher text, is translated and is referred to for the interpreter；
The client of attending a meeting, first translated speech sent for receiving the server, and play described the
One translated speech.
Preferably, the server includes: speech transcription module and machine translation module, in which:
The speech transcription module, for turning speechmaker's speech transcription at corresponding transcription text, and by described
It writes text and is sent to the machine translation module connected to it；
The machine translation module, for the transcription text to be translated into the cypher text, and the translation is literary
Originally it is sent to assistant's client.
Preferably, the server further include: voice synthetic module, in which:
The voice synthetic module, for being the second translated speech by the cypher text speech synthesis, second translation
Voice is transferred to the client terminal playing of attending a meeting.
Preferably, the client of attending a meeting includes the first display screen, and first display screen is for showing the translation text
This, and/or show that the server is sent to the transcription text of the client of attending a meeting, corresponding first translated speech.
Preferably, assistant's client includes second display screen, and the second display screen is for showing the translation text
The transcription text of this and the server to speechmaker's speech transcription.
Preferably, the system also includes first voice acquisition devices, in which:
First voice acquisition device is sent out for acquiring speechmaker's voice, and by collected speechmaker's voice
It send to the server connected to it.
Preferably, the system also includes second voice acquisition devices, in which:
Second voice acquisition device is sent out for acquiring first translated speech, and by first translated speech
It send to the server connected to it.
Preferably, the server is connect with the Client wireless network of attending a meeting.
Preferably, the speech transcription module includes WTK6900 chip.
Preferably, the machine translation module includes MT2523 chip.
Preferably, the voice synthetic module includes XFS3031CNP chip.
A kind of translation system, comprising: server, and the client of attending a meeting with the server communication connection, in which:
The server, speechmaker's voiced translation for will receive is cypher text, and the cypher text is synthesized
For the first translated speech, and it is sent to the client of attending a meeting；
The client of attending a meeting, first translated speech sent for receiving the server, and play described the
One translated speech.
Preferably, the system also includes the assistant's clients used by interpreter, for showing the cypher text；
The server is also used to receive the second translated speech that interpreter is exported based on the cypher text, and will be described
Second translated speech is sent to the client of attending a meeting, for second translated speech described in client terminal playing of attending a meeting.
Preferably, the server includes: speech transcription module, machine translation module and voice synthetic module, in which:
The speech transcription module, for turning speechmaker's speech transcription at corresponding transcription text, and by described
It writes text and is sent to the machine translation module connected to it；
The machine translation module, for the transcription text to be translated into the cypher text, and the translation is literary
Originally it is sent to the voice synthetic module；
The voice synthetic module, for being the first translated speech by the cypher text speech synthesis, first translation
Voice is transferred to the client terminal playing of attending a meeting.
Preferably, the client of attending a meeting includes the first display screen, and first display screen is for showing the translation text
This, and/or show that the server is sent to the transcription text of the client of attending a meeting, corresponding second translated speech.
Preferably, assistant's client includes second display screen, and the second display screen is for showing the translation text
The transcription text of this and the server to speechmaker's speech transcription.
A kind of translation system, comprising: server, and with assistant's client of the server communication connection and the client that attends a meeting
End, in which:
The server, for being the first transcription text to the speechmaker's speech transcription received, by first transcription
Text is translated as cypher text and is sent to assistant's client, and receives interpreter and turn over based on the cypher text exports first
Translate voice；
Assistant's client, is used by interpreter, for showing and modifying the cypher text；
The client of attending a meeting, for receiving turning based on first translated speech progress voice for the server transmission
The the second transcription text write, and show the second transcription text.
Preferably, the server includes: speech transcription module and machine translation module, in which:
The speech transcription module is used for speechmaker's speech transcription into corresponding first transcription text, will be described
First transcription text is sent to the machine translation module connected to it, and by the first translated speech transcription at corresponding
The second transcription text；
The machine translation module for the first transcription text to be translated into the cypher text, and is turned over described
Translation is originally sent to assistant's client.
Preferably, the server further include: voice synthetic module, in which:
The voice synthetic module, for being the second translated speech by the cypher text speech synthesis, second translation
Voice is transferred to the client terminal playing of attending a meeting.
A kind of translation system, comprising: server, and the client of attending a meeting with the server communication connection, in which:
The server, speechmaker's speech transcription for will receive is transcription text, is turned over based on the transcription text
It is translated into cypher text, and is sent to the client of attending a meeting；
The client of attending a meeting, the cypher text sent for receiving the server, and show the translation text
This.
Preferably, it the system also includes assistant's client, is used by interpreter, the institute sent for receiving the server
Transcription text and cypher text are stated, and shows the transcription text and/or cypher text, receives the cypher text of interpreter's modification,
And the cypher text of the modification is sent to the server.
Preferably, the server includes: speech transcription module and machine translation module, in which:
The speech transcription module, for turning speechmaker's speech transcription at corresponding transcription text, and by described
It writes text and is sent to the machine translation module connected to it；
The machine translation module, for the transcription text to be translated into the cypher text.
Preferably, the server further include: voice synthetic module, in which:
The voice synthetic module, for being the first translated speech by the cypher text speech synthesis, and/or by institute
The cypher text speech synthesis for stating modification is the second translated speech, and first translated speech and/or the second translated speech are passed
Transport to the client terminal playing of attending a meeting.
Compared with prior art, the application has the beneficial effect that
In this application, the translation system includes server, and assistant's client with server communication connection
With client of attending a meeting, speechmaker's voice is translated by server, cypher text is sent to assistant's client and is shown, is translated
The cypher text that shows by assistant's client of member, exports corresponding first translated speech of speechmaker's voice, and server is by first
Translated speech is sent to client of attending a meeting, for client terminal playing of attending a meeting.It can thus be seen that being translated during simultaneous interpretation
Member further can translate speechmaker's voice, reduce interpreter in conjunction with server to the translation result of speechmaker's voice
Working strength improve the accuracy rate of translation compared with the existing technology and reduce the cost of simultaneous interpretation.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of structural schematic diagram for translation system that the embodiment of the present application 1 provides；
Fig. 2 is a kind of structural schematic diagram for translation system that the embodiment of the present application 2 provides；
Fig. 3 is a kind of structural schematic diagram for translation system that the embodiment of the present application 3 provides；
Fig. 4 is a kind of structural schematic diagram for translation system that the embodiment of the present application 4 provides；
Fig. 5 is a kind of structural schematic diagram for translation system that the embodiment of the present application 5 provides；
Fig. 6 is a kind of structural schematic diagram for translation system that the embodiment of the present application 6 provides.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
As shown in Figure 1, for a kind of translation system disclosed in the embodiment of the present application 1, comprising: server 11, and with service
Assistant's client 12 of 11 communication connection of device and client 13 of attending a meeting, assistant's client 12 and client 13 of attending a meeting can be
It is multiple.
Server 11 receives speechmaker's voice, and translates to the speechmaker's voice received, by speechmaker's voice
Cypher text is sent to assistant's client 12.For example, the Chinese speech of speechmaker is translated as corresponding translator of English text.
Assistant's client 12 is used for interpreter, and the cypher text received is shown, for interpreter in translation speechmaker
As reference when voice.Server 11 can to speechmaker's voice realize simultaneous interpretation translation, translation speed quickly, can be good at for
Interpreter provides translation reference, or directly reads for interpreter and realize translation.
Interpreter translates speechmaker's voice with reference to the cypher text shown in assistant's client 12, and output first is turned over
Translate voice.
Server 11 receives the first translated speech of interpreter's output, and the first translated speech received is sent to and is attended a meeting
Client 13, such as server 11 and multiple clients 13 of attending a meeting are realized by local area network or private network and are communicated.Client of attending a meeting 13
The first translated speech received is played out, is listened to for personnel participating in the meeting, first played by listening to client 13 of attending a meeting
Translated speech can timely obtain the translation result of speechmaker's voice.Client of attending a meeting 13 can using tablet computer or its
He has the terminal, such as headset, wireless receiver etc. of receiver.
It can thus be seen that in the above-described embodiments, when translating to speechmaker's voice, passing through server 11 first
Speechmaker's voice is translated, cypher text is generated, refers to, reduce to interpreter's word when translating speechmaker's voice for interpreter
Remittance amount and professional requirement, and influence of speaker's accent to translation result is reduced, interpreter can combine server
To the translation result of speechmaker's voice, further speechmaker's voice is translated, therefore, reduce the cost of simultaneous interpretation and
Improve the accuracy rate of translation.
Specifically, in the above-described embodiments, server may include: speech transcription module, machine translation module and voice
Synthesis module.Speechmaker's speech transcription can be sent out at corresponding transcription text, and by transcription text by speech transcription module
It send to machine translation module, speech transcription module can also carry out transcription to the first translated speech that interpreter exports, generate and correspond to
The transcription text of first translated speech.The transcription text received can be translated into cypher text by machine translation module,
And cypher text is sent to assistant's client.The cypher text that can be exported machine translation module by voice synthetic module
Speech synthesis is the second translated speech, and the second translated speech is transmitted to client of attending a meeting, for client terminal playing of attending a meeting.Its
In, speech transcription module may include WTK6900 chip, and machine translation module may include MT2523 chip, speech synthesis mould
Block may include XFS3031CNP chip.
Specifically, in the above-described embodiments, client of attending a meeting may include display screen, for turning over for display server output
The transcription text for the first translated speech of correspondence that translation sheet and/or display server are sent.That is, client display screen of attending a meeting can
It is translated with the cypher text of display server output according to the needs of users, or the correspondence first that only display server is sent
The transcription text of voice, or the cypher text of display server output simultaneously, and the transcription text of corresponding first translated speech
This.Such as: display screen shows the corresponding transcription text (Chinese) of speechmaker's voice, while showing interpreter's translation, the first translation
The corresponding transcription text (English) of voice is realized double Subtitle Demonstrations, is watched for participant.
Specifically, in the above-described embodiments, assistant's client includes display screen, the display screen for show cypher text with
And server is to the transcription text of speechmaker's speech transcription.That is, assistant's client can only show service according to the demand of interpreter
The cypher text of device output, or again simultaneously display server to the transcription text of speechmaker's speech transcription.For example, display screen display
Show server to the cypher text (English) and display server that generate after speechmaker's voiced translation to speechmaker's speech transcription
Transcription text (Chinese).
Specifically, in the above-described embodiments, assistant's client can be connected by wired or wireless mode with server.Example
Such as, local area network/private network etc..Client of attending a meeting can be connected by way of wireless network with server.
Specifically, on the basis of the above embodiments, system can also include the first voice acquisition device and the second voice
Acquisition device.Speechmaker's voice is acquired by the first voice acquisition device, and collected speechmaker's voice is sent to service
Device；The first translated speech of interpreter's output is acquired by the second voice acquisition device, and collected first translated speech is sent out
It send to server.Wherein, the first voice acquisition device and the second voice acquisition device can use microphone, wired or wireless
It is connected to the server.
As shown in Fig. 2, for a kind of translation system disclosed in the embodiment of the present application 2, comprising: server 21, and with service
The client 22 of attending a meeting of 21 communication connection of device, the client 22 of attending a meeting can be multiple.
Server 21 receives speechmaker's voice, and translates to the speechmaker's voice received, generates cypher text, example
Such as, the Chinese speech of speechmaker is translated as corresponding translator of English text, and cypher text is synthesized into the first translated speech,
First translated speech is sent to client 22 of attending a meeting.
Client of attending a meeting 22 plays out the first translated speech received, listens to for personnel participating in the meeting, by listening to ginseng
The first translated speech that meeting client 22 plays can timely obtain the translation result of speechmaker's voice.Client of attending a meeting 22 can
With using tablet computer or other with receiving terminal, such as headset, wireless receiver etc..
It can thus be seen that in the above-described embodiments, when translating to speechmaker's voice, directly passing through server 21
Speechmaker's voice is translated, the first translated speech that output is played for client 22 of attending a meeting, in entire translation process, nothing
It needs interpreter to participate in, compared with the existing technology, reduces the cost of translation.
In order to further increase the accuracy rate of translation, as shown in figure 3, for a kind of translation system disclosed in the embodiment of the present application 3
System increases assistant's client 33 with 31 communication connection of server, the assistant visitor compared with translation system shown in Fig. 2
Family end 33 can be multiple.
Assistant's client 33 is used for interpreter, and the cypher text of speechmaker's voice can be sent to assistant visitor by server 31
Family end 33, assistant's client 33 show the cypher text received.
Interpreter translates speechmaker's voice with reference to the cypher text shown in assistant's client 33, and output second is turned over
Translate voice.
Server 31 receives the second translated speech of interpreter's output, and the second translated speech received is sent to and is attended a meeting
Client 32.Client of attending a meeting 32 can play out the second translated speech received, listen to for personnel participating in the meeting.That is, with
Family can select the first translated speech of listening server translation output or the second translated speech of interpreter's output according to demand.
In application scenes, the first translated speech is complementary with the second translated speech, such as speechmaker's atmosphere tune during speech
When chatting about, server 31 cannot translate the voice for atmosphere of talking in professional jargon well, then provided by interpreter and intervene, play the of interpreter's translation
Two translated speech.
In this embodiment, server 31 can realize that simultaneous interpretation and friendship pass, if interpreter translates knot to server 31 when handing over biography
When fruit is not approved, it can be provided to hand over to pass by interpreter and translated.
It can thus be seen that on the basis of above-described embodiment 2, embodiment 3 is further by assistant's client 33 to turning over
Translation is originally shown, when handing over biography with special applications scene, cooperates interpreter to improve translation accurately using assistant's client 33
Rate；Also it refers to, reduces to interpreter's vocabulary and professional requirement when translating speechmaker's voice for interpreter, and reduce
Therefore influence of speaker's accent to translation result reduces the cost of simultaneous interpretation and improves the accuracy rate of translation.
Specifically, in the above-described embodiments, server 31 may include: speech transcription module 311, machine translation module
312 and voice synthetic module 313.By speech transcription module 311 can by speechmaker's speech transcription at corresponding transcription text,
And transcription text is sent to machine translation module 312.The transcription text received can be turned over by machine translation module 312
It is translated into cypher text, and cypher text is sent to voice synthetic module 313.It can will be translated by voice synthetic module 313
Text voice synthesizes the first translated speech, for client terminal playing of attending a meeting.Wherein, speech transcription module 311 may include
WTK6900 chip, machine translation module 312 may include MT2523 chip, and voice synthetic module 313 may include
XFS3031CNP chip.
Specifically, in the above-described embodiments, client of attending a meeting may include display screen, for showing cypher text, and/or
Display server is sent to the transcription text of client of attending a meeting, corresponding second translated speech.
Specifically, in the above-described embodiments, assistant's client may include display screen, for showing cypher text and service
Transcription text of the device to speechmaker's speech transcription.
It is understood that client of attending a meeting includes display screen and pronunciation receiver, which be can be
Headset, wireless receiver, and display screen can be with pronunciation receiver and separate.I.e. display screen is placed on desktop or by attending a meeting
Client handheld, and pronunciation receiver is worn on and attends a meeting on client's ear；Certainly the two can also become one, such as using flat
Plate computer etc. is as client of attending a meeting.In the absence of conflict, the client of attending a meeting of each embodiment of the application can be as above-mentioned
Setting.
Similarly, on the basis of above-described embodiment 2 or embodiment 3, system can also include the first voice acquisition device and
Second voice acquisition device acquires speechmaker's voice by the first voice acquisition device, and collected speechmaker's voice is sent out
It send to server；The second translated speech of interpreter's output is acquired by the second voice acquisition device, and collected second is turned over
It translates voice and is sent to server.Wherein, the first voice acquisition device and the second voice acquisition device can use microphone, have
Line is wirelessly connected to the server.
As shown in figure 4, for a kind of translation system disclosed in the embodiment of the present application 4, comprising: server 41, and with service
Assistant's client 42 of 41 communication connection of device and client 43 of attending a meeting, assistant's client 42 and client 43 of attending a meeting can be
It is multiple.
Server 41 receives speechmaker's voice, carries out speech transcription to the speechmaker's voice received, generates the first transcription
Then first transcription text is translated as cypher text, and cypher text is sent to assistant's client 42 by text.
Assistant's client 42 is used for interpreter, and the cypher text received is shown, for interpreter in translation speechmaker
As reference when voice.
Interpreter translates speechmaker's voice with reference to the cypher text shown in assistant's client 42, and output first is turned over
Translate voice.
Server 41 receives the first translated speech of interpreter's output, is second turn by the first translated speech transcription received
Text is write, and the second transcription text is sent to client 43 of attending a meeting, client 43 is shown for attending a meeting, and passes through client 43 of attending a meeting
Second transcription text of display, user can obtain the corresponding translation result of speechmaker's voice.
It can thus be seen that in the above-described embodiments, when translating to speechmaker's voice, passing through server 41 first
Transcription and translation are carried out to speechmaker's voice, cypher text is generated, is referred to for interpreter when translating speechmaker's voice, is reduced pair
Interpreter's vocabulary and professional requirement, and influence of speaker's accent to translation result is reduced, interpreter can combine
Server further translates the translation result of speechmaker's voice to speechmaker's voice, therefore, reduces simultaneous interpretation
Cost and the accuracy rate for improving translation.Meanwhile in this embodiment, client of attending a meeting receives cypher text, and text is with subtitle
Form show, read and understand convenient for the client that attends a meeting, also avoid translating that some too fast key contents cannot catch asks
Topic.
Specifically, in the above-described embodiments, server 41 may include: speech transcription module 411, machine translation module
412 and voice synthetic module 413.It can be by speechmaker's speech transcription at corresponding first transcription by speech transcription module 411
Text, and the first transcription text is sent to machine translation module 412.What speech transcription module 411 can also export interpreter
First translated speech transcription is the second transcription text of corresponding first translated speech, and for attending a meeting, client is shown.It is turned over by machine
Cypher text can be translated into for the first transcription text received by translating module 412, and cypher text is sent to speech synthesis
Module 413.It can be the second translated speech by cypher text speech synthesis by voice synthetic module 413, for client of attending a meeting
It plays.Wherein, speech transcription module 411 may include WTK6900 chip, and machine translation module 412 may include MT2523 core
Piece, voice synthetic module 413 may include XFS3031CNP chip.
Specifically, in the above-described embodiments, client of attending a meeting may include display screen, for showing cypher text, and/or
Display server is sent to the second transcription text of client of attending a meeting, corresponding first translated speech.
Specifically, in the above-described embodiments, assistant's client may include display screen, for showing cypher text and service
First transcription text of the device to speechmaker's speech transcription.
Similarly, on the basis of above-described embodiment 4, system can also include that the first voice acquisition device and the second voice are adopted
Acquisition means acquire speechmaker's voice by the first voice acquisition device, and collected speechmaker's voice are sent to server；
The first translated speech of interpreter's output is acquired by the second voice acquisition device, and collected first translated speech is sent to
Server.Wherein, the first voice acquisition device and the second voice acquisition device can use microphone, wired or wireless connection
To the server.
As shown in figure 5, for a kind of translation system disclosed in the embodiment of the present application 5, comprising: server 51, and with service
The client 52 of attending a meeting of 51 communication connection of device, the client 52 of attending a meeting can be multiple.
Server 51 receives speechmaker's voice, is transcription text by the speechmaker's speech transcription received, by transcription text
Cypher text is translated into, and cypher text is sent to client 52 of attending a meeting.
Client of attending a meeting 52 shows the cypher text received, checks for personnel participating in the meeting.
It can thus be seen that in the above-described embodiments, when translating to speechmaker's voice, directly passing through server 51
Transcription and translation are carried out to speechmaker's voice, export the cypher text for the display of client 52 of attending a meeting, in entire translation process,
It being participated in without interpreter, user can obtain the translation result of speechmaker's voice by the cypher text shown in client 52 of attending a meeting,
Compared with the existing technology, the cost of translation is reduced.
In order to further increase the accuracy rate of translation, as shown in fig. 6, for a kind of translation system disclosed in the embodiment of the present application 6
System increases assistant's client 63 with 61 communication connection of server, the assistant visitor compared with translation system shown in fig. 5
Family end 63 can be multiple.
Assistant's client 63 is used for interpreter, and server 61 can send out the transcription text and cypher text of speechmaker's voice
It send to assistant's client 63, assistant's client 63 shows the transcription text and cypher text that receive.
Interpreter modifies to cypher text with reference to the transcription text and cypher text that show in assistant's client 63, and
Modified cypher text is sent to server 61, the modified cypher text received is sent to and attends a meeting by server 61
Client 62, for attending a meeting, client 62 is shown, user can be by the modified cypher text that shows in client 62 of attending a meeting
Obtain the translation result of speechmaker's voice.
It can thus be seen that on the basis of above-described embodiment 5, embodiment 6 is further by assistant's client 63 to turning
Write text and cypher text shown, referred to for interpreter when modifying cypher text, reduce to interpreter's vocabulary and specially
The requirement of industry, and influence of speaker's accent to translation result is reduced, therefore, reduces the cost of simultaneous interpretation and mention
The high accuracy rate of translation.Meanwhile in this embodiment, client of attending a meeting receives cypher text, and text is shown in the form of subtitles
Show, reads and understand convenient for the client that attends a meeting, also avoid translating the problem of some too fast key contents cannot be caught.
Specifically, in the above-described embodiments, server 61 may include: speech transcription module 611, machine translation module
612 and voice synthetic module 613.By speech transcription module 611 can by speechmaker's speech transcription at corresponding transcription text,
And transcription text is sent to machine translation module 612.The transcription text received can be turned over by machine translation module 612
It is translated into cypher text, and cypher text is sent to voice synthetic module 613.It can will be translated by voice synthetic module 613
Text voice synthesizes the first translated speech, for client terminal playing of attending a meeting.After voice synthetic module 613 can also modify interpreter
Cypher text speech synthesis be the second translated speech, for client terminal playing of attending a meeting.Wherein, speech transcription module 611 can wrap
WTK6900 chip is included, machine translation module 612 may include MT2523 chip, and voice synthetic module 613 may include
XFS3031CNP chip.
Specifically, in the above-described embodiments, client of attending a meeting may include display screen, for showing cypher text, and/or
Show the modified cypher text of interpreter.
Specifically, in the above-described embodiments, assistant's client may include display screen, for showing cypher text and service
Transcription text of the device to speechmaker's speech transcription.
Similarly, on the basis of above-described embodiment 5 or embodiment 6, system can also include the first voice acquisition device, lead to
The first voice acquisition device acquisition speechmaker's voice is crossed, and collected speechmaker's voice is sent to server.Wherein, first
Voice acquisition device can use microphone, wired or wireless to be connected to the server.
In order to more specifically emphasize that the independence implemented, this specification are related to number of modules or unit.For example, mould
Block or unit can be realized that the hardware circuit includes special VLSI circuit or gate array, such as logic chip, crystal by hardware circuit
Pipe or other components.Module or unit can also be realized in programmable computer hardware, for example field is imitated programmable gate array, can be compiled
Journey array logic, programmable logic device etc..
" embodiment " mentioned by this specification or similar term indicate characteristic related with embodiment, structure or feature,
Including in at least embodiment of the application.Therefore, this specification occurs term " in one embodiment " " is being implemented
In example " and similar to term possibility but it is not necessarily all direction identical embodiment.
Furthermore herein described characteristic, structure or feature can combine in any way in one or more embodiments.
Those of ordinary skill in the related art can be seen that the application, even if not utilizing wherein one or more specific details, or benefit
It is also implementable with other methods, component, material etc..It on the other hand, is the application that avoids confusion, well known structure, material or behaviour
It does not have a detailed description.
The foregoing description of the disclosed embodiments makes professional and technical personnel in the field can be realized or use the application.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the application.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (23)
1. a kind of translation system characterized by comprising server, and assistant's client with the server communication connection
With client of attending a meeting, in which:
The server sends out the cypher text of speechmaker's voice for translating to the speechmaker's voice received
It send to assistant's client, and receives first translated speech of the interpreter based on speechmaker's voice output；
Assistant's client, is used by interpreter, for showing the cypher text, is translated and is referred to for the interpreter；
The client of attending a meeting, first translated speech sent for receiving the server, and play described first and turn over
Translate voice.
2. system according to claim 1, which is characterized in that the server includes: that speech transcription module and machine turn over
Translate module, in which:
The speech transcription module is used for speechmaker's speech transcription into corresponding transcription text, and the transcription is literary
Originally it is sent to the machine translation module connected to it；
The machine translation module for the transcription text to be translated into the cypher text, and the cypher text is sent out
It send to assistant's client.
3. system according to claim 2, which is characterized in that the server further include: voice synthetic module, in which:
The voice synthetic module, for being the second translated speech, second translated speech by the cypher text speech synthesis
It is transferred to the client terminal playing of attending a meeting.
4. system according to claim 1, which is characterized in that the client of attending a meeting includes the first display screen, and described the
One display screen is for showing that the cypher text, and/or the display server are sent to the client of attending a meeting, corresponding institute
State the transcription text of the first translated speech.
5. system according to claim 1, which is characterized in that assistant's client includes second display screen, and described
Two display screens are for showing the cypher text and the server to the transcription text of speechmaker's speech transcription.
6. system described according to claim 1~any one of 5, which is characterized in that further include: the first voice collecting dress
It sets, in which:
First voice acquisition device is sent to for acquiring speechmaker's voice, and by collected speechmaker's voice
The server connected to it.
7. system according to claim 6, which is characterized in that further include: the second voice acquisition device, in which:
Second voice acquisition device is sent to for acquiring first translated speech, and by first translated speech
The server connected to it.
8. system according to claim 7, which is characterized in that the server and the Client wireless network company that attends a meeting
It connects.
9. system according to claim 2, which is characterized in that the speech transcription module includes WTK6900 chip.
10. system according to claim 2, which is characterized in that the machine translation module includes MT2523 chip.
11. system according to claim 3, which is characterized in that the voice synthetic module includes XFS3031CNP chip.
12. a kind of translation system characterized by comprising server, and the client that attends a meeting with the server communication connection
End, in which:
The server, speechmaker's voiced translation for will receive are cypher text, and the cypher text is synthesized the
One translated speech, and it is sent to the client of attending a meeting；
The client of attending a meeting, first translated speech sent for receiving the server, and play described first and turn over
Translate voice.
13. system according to claim 12, which is characterized in that further include the assistant's client used by interpreter, be used for
Show the cypher text；
The server, is also used to receive the second translated speech that interpreter is exported based on the cypher text, and by described second
Translated speech is sent to the client of attending a meeting, for second translated speech described in client terminal playing of attending a meeting.
14. system according to claim 12, which is characterized in that the server includes: that speech transcription module, machine turn over
Translate module and voice synthetic module, in which:
The speech transcription module is used for speechmaker's speech transcription into corresponding transcription text, and the transcription is literary
Originally it is sent to the machine translation module connected to it；
The machine translation module for the transcription text to be translated into the cypher text, and the cypher text is sent out
It send to the voice synthetic module；
The voice synthetic module, for being the first translated speech, first translated speech by the cypher text speech synthesis
It is transferred to the client terminal playing of attending a meeting.
15. system according to claim 13, which is characterized in that the client of attending a meeting includes the first display screen, described
First display screen is for showing that the cypher text, and/or the display server are sent to the client of attending a meeting, correspondence
The transcription text of second translated speech.
16. system according to claim 13, which is characterized in that assistant's client includes second display screen, described
Second display screen is for showing the cypher text and the server to the transcription text of speechmaker's speech transcription.
17. a kind of translation system characterized by comprising server, and assistant's client with the server communication connection
With client of attending a meeting, in which:
The server, for being the first transcription text to the speechmaker's speech transcription received, by the first transcription text
It is translated as cypher text and is sent to assistant's client, and receive the first translation language that interpreter is exported based on the cypher text
Sound；
Assistant's client, is used by interpreter, for showing and modifying the cypher text；
The client of attending a meeting carries out speech transcription based on first translated speech for receive that the server sends
Second transcription text, and show the second transcription text.
18. system according to claim 17, which is characterized in that the server includes: speech transcription module and machine
Translation module, in which:
The speech transcription module is used for speechmaker's speech transcription at corresponding first transcription text, by described first
Transcription text is sent to the machine translation module connected to it, and by the first translated speech transcription at corresponding described
Second transcription text；
The machine translation module, for the first transcription text to be translated into the cypher text, and the translation is literary
Originally it is sent to assistant's client.
19. system according to claim 18, which is characterized in that the server further include: voice synthetic module,
In:
The voice synthetic module, for being the second translated speech, second translated speech by the cypher text speech synthesis
It is transferred to the client terminal playing of attending a meeting.
20. a kind of translation system characterized by comprising server, and the client that attends a meeting with the server communication connection
End, in which:
The server, speechmaker's speech transcription for will receive is transcription text, is translated into based on the transcription text
Cypher text, and it is sent to the client of attending a meeting；
The client of attending a meeting, the cypher text sent for receiving the server, and show the cypher text.
21. system according to claim 20, which is characterized in that further include assistant's client, used by interpreter, for connecing
The transcription text and cypher text that the server is sent are received, and shows the transcription text and/or cypher text, is received
The cypher text of interpreter's modification, and the cypher text of modification is sent to the server.
22. system according to claim 20, which is characterized in that the server includes: speech transcription module and machine
Translation module, in which:
The speech transcription module is used for speechmaker's speech transcription into corresponding transcription text, and the transcription is literary
Originally it is sent to the machine translation module connected to it；
The machine translation module, for the transcription text to be translated into the cypher text.
23. system according to claim 22, which is characterized in that the server further include: voice synthetic module,
In:
The voice synthetic module, for being the first translated speech, and/or turning over modification by the cypher text speech synthesis
This speech synthesis of translation is the second translated speech, and first translated speech and/or the second translated speech are transferred to the ginseng
It can client terminal playing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820906466.1U CN208622096U (en) | 2018-06-06 | 2018-06-06 | A kind of translation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820906466.1U CN208622096U (en) | 2018-06-06 | 2018-06-06 | A kind of translation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208622096U true CN208622096U (en) | 2019-03-19 |
Family
ID=65702961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201820906466.1U Active CN208622096U (en) | 2018-06-06 | 2018-06-06 | A kind of translation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208622096U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110166729A (en) * | 2019-05-30 | 2019-08-23 | 上海赛连信息科技有限公司 | Cloud video-meeting method, device, system, medium and calculating equipment |
| CN110609629A (en) * | 2019-10-20 | 2019-12-24 | 合肥马道信息科技有限公司 | Real-time long voice transcription system and method based on mouse |
| CN111142822A (en) * | 2019-12-27 | 2020-05-12 | 深圳小佳科技有限公司 | Simultaneous interpretation conference method and system |
| CN112232092A (en) * | 2020-10-15 | 2021-01-15 | 安徽听见科技有限公司 | Simultaneous interpretation method and system with machine and artificial cooperation mode |
| CN114338643A (en) * | 2020-09-25 | 2022-04-12 | 北京有竹居网络技术有限公司 | Data processing method, device, client, server and storage medium |
-
2018
- 2018-06-06 CN CN201820906466.1U patent/CN208622096U/en active Active
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110166729A (en) * | 2019-05-30 | 2019-08-23 | 上海赛连信息科技有限公司 | Cloud video-meeting method, device, system, medium and calculating equipment |
| CN110609629A (en) * | 2019-10-20 | 2019-12-24 | 合肥马道信息科技有限公司 | Real-time long voice transcription system and method based on mouse |
| CN111142822A (en) * | 2019-12-27 | 2020-05-12 | 深圳小佳科技有限公司 | Simultaneous interpretation conference method and system |
| CN114338643A (en) * | 2020-09-25 | 2022-04-12 | 北京有竹居网络技术有限公司 | Data processing method, device, client, server and storage medium |
| CN112232092A (en) * | 2020-10-15 | 2021-01-15 | 安徽听见科技有限公司 | Simultaneous interpretation method and system with machine and artificial cooperation mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN208622096U (en) | A kind of translation system | |
| CN105512113B (en) | AC system speech translation system and interpretation method | |
| JP5564459B2 (en) | Method and system for adding translation to a video conference | |
| CN202838331U (en) | Long-distance synchrony translation system | |
| Green et al. | Enhancement of temporal periodicity cues in cochlear implants: Effects on prosodic perception and vowel identification | |
| CN109614628A (en) | A kind of interpretation method and translation system based on Intelligent hardware | |
| CN203338350U (en) | Machine simultaneous interpretation system | |
| CN110166729B (en) | Cloud video conference method, device, system, medium and computing equipment | |
| Xia et al. | Spatial release of cognitive load measured in a dual-task paradigm in normal-hearing and hearing-impaired listeners | |
| CN107527623A (en) | Screen transmission method, device, electronic equipment and computer-readable recording medium | |
| CN106792013A (en) | A kind of method, the TV interactive for television broadcast sounds | |
| Wang et al. | Speaking rhythmically improves speech recognition under “cocktail-party” conditions | |
| Humes et al. | Exploring use of the coordinate response measure in a multitalker babble paradigm | |
| US10909332B2 (en) | Signal processing terminal and method | |
| Remael | Media accessibility | |
| US20200312302A1 (en) | System for improving dysarthria speech intelligibility and method thereof | |
| CN107277691A (en) | Multichannel audio player method, system and audio frequency net gate way apparatus based on cloud | |
| CN201698607U (en) | Interactive English teaching examination device for voice classroom | |
| CN103617753A (en) | Audio processing method and system for synchronous classroom | |
| Hall et al. | Intelligibility and listener preference of telephone speech in the presence of babble noise | |
| CN109300478A (en) | A kind of auxiliary Interface of person hard of hearing | |
| CN109802968B (en) | Conference speaking system | |
| CN208094741U (en) | A kind of intelligent microphone based on speech recognition technology | |
| CN205430457U (en) | Multi -media synchronized play system | |
| CN105491302A (en) | Audio signal output method and device, terminal, and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |